Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 984 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.4422. Min Act: -0.0000

Data Index: 1151587 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.4313. Min Act: -0.0000

Data Index: 220365 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.3726. Min Act: -0.0000

Data Index: 165244 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1787. Min Act: -0.0000

Data Index: 774399 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.2263. Min Act: -0.0000

Data Index: 696800 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1056527 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.2084. Min Act: -0.0000

Data Index: 1379417 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1640681 (Python Code)

Max Activating Token Index: 652

Text #8

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1098. Min Act: -0.0000

Data Index: 1349482 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0421. Min Act: -0.0000

Data Index: 229438 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0895. Min Act: -0.0000

Data Index: 532505 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1561827 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1384065 (Python Code)

Max Activating Token Index: 452

Text #13

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9985. Min Act: -0.0000

Data Index: 811916 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0635. Min Act: -0.0000

Data Index: 486023 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0772. Min Act: -0.0000

Data Index: 411182 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9919. Min Act: -0.0000

Data Index: 395409 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1276026 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1449032 (Python Code)

Max Activating Token Index: 483

Text #19

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0055. Min Act: -0.0000

Data Index: 337788 (C4 (Web Text))

Max Activating Token Index: 195